Tao Peng


ALBERT-BiLSTM for Sequential Metaphor Detection
Shuqun Li | Jingjie Zeng | Jinhui Zhang | Tao Peng | Liang Yang | Hongfei Lin
Proceedings of the Second Workshop on Figurative Language Processing

In our daily life, metaphor is a common way of expression. To understand the meaning of a metaphor, we should recognize the metaphor words which play important roles. In the metaphor detection task, we design a sequence labeling model based on ALBERT-LSTM-softmax. By applying this model, we carry out a lot of experiments and compare the experimental results with different processing methods, such as with different input sentences and tokens, or the methods with CRF and softmax. Then, some tricks are adopted to improve the experimental results. Finally, our model achieves a 0.707 F1-score for the all POS subtask and a 0.728 F1-score for the verb subtask on the TOEFL dataset.


POC-NLW Template for Chinese Word Segmentation
Bo Chen | Weiran Xu | Tao Peng | Jun Guo
Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing